Exposed Google API keys previously not considered secrets can now inadvertently grant attackers access to sensitive Gemini ...

Exposed Google Cloud API keys in public JavaScript may now authenticate Gemini API calls, risking data exposure and runaway ...

Google API keys for services like Maps embedded in accessible client-side code could be used to authenticate to the Gemini AI ...

Research reveals 2,863 public Google API keys can access Gemini endpoints, enabling data exposure and massive billing abuse.

API key exploitation is more than hypothetical. In a different context, a student who reportedly exposed a GCP API key on GitHub last June was left nursing a $55,444 bill (later waived by Google) ...

Over 2,800 exposed Google API keys may allow unauthorized Gemini AI access, risking data leaks and massive API charges.

Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in ...

Gemini 3.1 Pro boosts reasoning and agent-style AI, aiming to solve complex tasks, cut prompt babysitting, and turn Gemini from a chatbot into a real productivity engine.

Google says hackers are abusing Gemini to speed up cyberattacks, from target research to post-breach troubleshooting. The risk is faster iteration and model extraction, not brand-new tactics, which ...